Chips fabricated using a 5 nanometer process are still pretty new, but IBM is ready to show off the next big thing. As is often the case with processor technology, the next big thing is actually smaller.

IBM has produced the world’s first 2nm chips.

The breakthrough chip squeezes 50 billion transistors into a miniscule area of 150 square millimeters. That puts its transistor density at just over 330 million transistors per square millimeter which is about 94% greater than the 5nm chips currently on the market (including Apple’s M1 and Huawei’s Kirin 9000 processors).

It’s also 14% greater than the upcoming chips based on TSMC’s 3nm process, which are due to start shipping some time next year.

IBM claims that the performance and efficiency gains over 7nm are substantial. When computational muscle is the top priority, its 2nm performs 45% better. When extended battery life is more important, IBM’s 2nm is capable of delivering performance on par with a 7nm chip while using about 75% less power.

In its press release, IBM claims that smartphones with 2nm chips will theoretically be able to offer up to four days of battery life, although it’s likely that real-world performance won’t be quite so impressive. Radios and the big, bright, beautiful screens on our phones and are still the among the biggest drains on a phone’s battery, making the processor just part of the equation.

As for when you might actually see chips based on IBM’s 2nm designs in devices you can buy, that’s hard to say. IBM no longer manufactures processors at scale, having sold that part of its business to Global Foundries several years ago.

The company has chipmaking partnerships with both Intel and Samsung, though. Intel has previously announced a goal of shipping 2nm chips by 2027 and IBM’s latest breakthrough could help make that a reality. It could also help Samsung produce a successor to the 3nm chips it’s preparing to produce at scale in 2022.

via AnandTech 

Support Liliputing

Liliputing's primary sources of revenue are advertising and affiliate links (if you click the "Shop" button at the top of the page and buy something on Amazon, for example, we'll get a small commission).

But there are several ways you can support the site directly even if you're using an ad blocker* and hate online shopping.

Contribute to our Patreon campaign

or...

Contribute via PayPal

* If you are using an ad blocker like uBlock Origin and seeing a pop-up message at the bottom of the screen, we have a guide that may help you disable it.

Join the Conversation

8 Comments

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

    1. @penguinx86 said: “2nm is 70% smaller than Intel’s 7nm chips.”

      Not in area, which is the important metric: 2mm^2 is 100((77)/(2*2)=1,225% smaller than 7mm^2.

      1. No. This number doesn’t relate to anything real. Anandtech have a table showing logic density for the various process nodes, which confirms Penguin’s comment.

  1. I am pretty sure that OEMs will ship phones with 1500 mAh or less to compensate for the power efficiency.

    1. Dang it, he’s right!
      Or they will keep the same battery, but instead use more thirstier processor, display, radios… or a combination of the three. Real-world use case be damned :'(

  2. Exactly this. Display power generally dominates total system power consumption. Whoever wrote up that bio is trying too hard to create. Plus, IBM’s stock has been receding since around 2012. So whenever they make some big promise about such and such, I take it with a boulder of salt. Making a one-off prototype is one thing. That happens sometimes as early as a decade in advance to real-world production! Actually delivering it consistently and competitively is a whole other matter entirely. The other big thing that has the alarm bells going off in my head for me right now is that their transistor density for 2nm is suspiciously close to TSMC’s 3nm. I would not be surprised if Intel, through IBM, is trying to one up TSMC in perceived competitive edge who has used differing specifications to quote node size. And I would not be surprised if they are trying to reclaim their node leadership by stretching the truth a bit. Besides, TSMC’s 3nm is already entering into production in 2022. When is IBM/Intel’s 2nm even coming? If it’s 2027, they might as well throw in the towel because TSMC will have already beat them to market with their comparable 3nm process by a good half a decade.

  3. I imagine this has to be the most lilliputian technology featured here so far.
    It looks like their claim of 4 days of battery life seems to be calculated from 1 day of battery life on 7 nm phones, and a 75% power reduction, so your point about screens and radios makes their claim pretty bad on just the napkin math. Their next point in the press release, more efficient data centers, sounds plausible and pretty great.

    1. My first computer had a 6502 processor with 8um technology. The IBM 2nm technology is 4000 times smaller. Liliputing to the max!